Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    lacking substance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ppl
    0.58
     đc
    0.55
     yg
    0.52
     detd
    0.49
    ㄉ
    0.46
     compds
    0.45
     solns
    0.45
     महत्त्वपूर्ण
    0.45
     kttt
    0.44
    ㅈ
    0.44
    POSITIVE LOGITS
    —
    0.43
    </sup>
    0.42
     *
    0.41
     recyclable
    0.40
    --
    0.39
    ◊
    0.38
    ________________
    0.37
      
    0.36
    ("
    0.36
    ("");
    0.36
    Act Density 0.001%

    No Known Activations